Skip to main content
Glama
lyonzin

knowledge-rag

by lyonzin
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to knowledge-rag

No user-submitted related servers found.

    Related Servers

    • devrag

      tomohiro-owada
      F
      license
      Not graded
      quality
      C
      maintenance
      A lightweight RAG (Retrieval-Augmented Generation) system for Claude Code that enables semantic search over local markdown documents via MCP tools, saving tokens and time.
      64
      -

    • mcp-local-rag

      damoqiongqiu
      A
      license
      A
      quality
      C
      maintenance
      A fully local RAG MCP server for semantic code search and code intelligence, using AST-level chunking and hybrid search to pinpoint functions, classes, and APIs. No cloud, no API keys, zero setup.
      16
      51 npm
      13
      MIT

    • Melchizedek

      louis49
      A
      license
      A
      quality
      C
      maintenance
      Persistent memory for Claude Code. Automatically indexes every conversation and provides production-grade hybrid search (BM25 + vectors + reranker) via MCP tools. 100% local, zero config, zero API keys, zero invoice.
      16
      30 npm
      7
      MIT

    • arcana-mcp

      samelie
      A
      license
      A
      quality
      C
      maintenance
      Semantic vector DB as an MCP server for Claude Code — SQLite + FTS5 + local ONNX embeddings. Gives Claude persistent, searchable project knowledge across conversations.
      12
      25 PyPI
      MIT
    Deploy Server
    Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

    TDQS

    A4.9/5.0

    Scored across 13 tools

    Disambiguation5/5

    Each tool targets a distinct action/resource: browsing (list_documents, list_categories), retrieval (search_knowledge, search_similar, get_document), ingestion (add_document, add_from_url), mutation (update_document, remove_document), and maintenance (reindex_documents, get_reindex_status, get_index_stats, evaluate_retrieval). The descriptions explicitly cross-reference sibling tools to steer selection (e.g., search_similar vs search_knowledge, get_document vs search_knowledge). No two tools appear to do the same thing.

    Naming Consistency5/5

    All 13 tools follow a consistent snake_case verb_noun pattern (list_*, get_*, add_*, search_*, update_*, remove_*, reindex_*, evaluate_*). Naming aligns cleanly with the underlying operation and resource, with no mixed conventions or vague verbs.

    Tool Count5/5

    13 tools sits squarely in the ideal 3-15 range for a RAG knowledge-base server. The set covers browsing, searching, ingestion, lifecycle mutation, and operational maintenance without redundant or filler tools.

    Completeness5/5

    Full lifecycle is covered: create (add_document, add_from_url), read (list_documents, get_document, search_knowledge, search_similar, list_categories), update (update_document), delete (remove_document), plus reindex/maintenance (reindex_documents, get_reindex_status, get_index_stats) and quality auditing (evaluate_retrieval). No obvious dead ends for the stated domain.

    Maintenance

    ActivityActive
    ResponsivenessWithin a week

    Resources